agentleFS
Sign inStart free
sametbrrsametbrr/github-manager/AGENTS.md

github-manager

AGENTS.md0 starsChanged 12 days agoMITView on GitHub

Agent Skills plugin (Claude Code and Codex) that audits and strengthens any GitHub account: profile fields, profile README, repo descriptions, topics, license, project READMEs and release workflows. Standards are generic; user preferences come from a config file.

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,542 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository8 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Keep version equal in both manifests and every SKILL.md metadata.version.

    line 28
  2. Distinctive:

    Never commit or push without explicit approval from the maintainer.

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

github-manager — agent guide

Agent Skills plugin (Claude Code and Codex) that audits and strengthens any GitHub account: profile fields, profile README, repo descriptions, topics, license, project READMEs and release workflows. Standards are generic; user preferences come from a config file.

Layout

  • skills/<name>/SKILL.md: seven skills (gh-audit, gh-onboard, gh-normalize, profile-bio, profile-readme, readme-standard, release-workflow). Each keeps its standard in its own references/; skills reach siblings with ../<skill>/references/....
  • skills/gh-audit/references/config.md: the config schema and defaults. Update it, both READMEs and the readme-standard SKILL.md table together when a key changes.
  • skills/*/agents/openai.yaml: Codex policy for the five write-capable skills (allow_implicit_invocation: false, matching disable-model-invocation: true).
  • agents/*.md: read-only analyzer subagents. Callers pass them the standard path and the config; no ${CLAUDE_PLUGIN_ROOT} in skill or agent bodies.
  • skills/release-workflow/assets/templates/release-*.yml + scripts/add-release-workflow.sh: release templates and the installer (placeholders __DEFAULT_BRANCH__, __CSPROJ__, …).
  • .claude-plugin/plugin.json (version source of truth) and .codex-plugin/plugin.json.
  • .github/workflows/release.yml: tags v<version> from .claude-plugin/plugin.json on push to main.

Rules

  • Host-neutral wording; no hardcoded ~/.claude/... paths, no host tool names, no personal data or account-specific examples in the standards.
  • User config lives in $GITHUB_MANAGER_HOME or ~/.agents/github-manager/, never in the plugin dir.
  • Skills never write to GitHub or commit/push without explicit user approval; templates never paste commit text into shell commands.
  • Keep version equal in both manifests and every SKILL.md metadata.version; add a CHANGELOG.md entry and update both READMEs (EN + TR mirror) with every bump.
  • Never commit or push without explicit approval from the maintainer.

Checks

  • claude plugin validate .
  • plans/tools/codex_smoke.sh . <skills…> from the skill-hub workspace (skills with allow_implicit_invocation: false are installed but not listed in the implicit skill list).
  • bash -n skills/release-workflow/scripts/add-release-workflow.sh, then run it with --detect and --stdout against temp clones under /tmp; lint the output with actionlint.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free